Models

Compare models by price, context, and capability. Official uses the model maker's published price as its base.

Alibaba Cloud

Type

All77

qwen3-coder-flash

Available

CodePrompt CacheCached inputless

TokenLab price— Discount: —
Official price: Input$0.1471Output$0.5882/1M

qwen3.8-2.4t-a95b

Available

JSON modePrompt CacheTool useCached inputless

TokenLab price— Discount: —
Official price: Input$1.76Output$5.29/1M

qwen3.8-27b

Available

JSON modePrompt CacheTool useVisionCached inputless

TokenLab price— Discount: —
Official price: Input$0.4412Output$1.76/1M

qwen3.8-flash

Available

JSON modePrompt CacheTool useVisionCached inputless

TokenLab price— Discount: —
Official price: Input$0.1176Output$0.3971/1M

qwen3.8-max

Available

JSON modePrompt CacheTool useVisionCached inputless

TokenLab price— Discount: —
Official price: Input$1.76Output$5.29/1M

qwen3.6-max-preview

DeprecatedAvailable

Tool use

TokenLab price— Discount: —
Official price: Input$1.43Output$8.60/1M

qwen-flash

Available

Prompt CacheCached inputless

TokenLab price— Discount: —
Official price: Input$0.0221Output$0.2206/1M

qwen-plus

Available

Prompt CacheCached inputless

TokenLab price— Discount: —
Official price: Input$0.1176Output$0.2941/1M

qwen3.5-flash

Available

Prompt CacheCached inputless

TokenLab price— Discount: —
Official price: Input$0.0294Output$0.2941/1M

qwen3.5-plus

Available

Prompt CacheCached inputless

TokenLab price— Discount: —
Official price: Input$0.1176Output$0.7059/1M

qwen3.7-max

Available

Prompt CacheCached inputless

TokenLab price— Discount: —
Official price: Input$1.76Output$5.29/1M

Model	Context	Max output	Official price	TokenLab price	Discount
qwen3-coder-flashCodePrompt Cache	998K	64K	Input$0.1471Output$0.5882/1M	—	—
qwen3.8-2.4t-a95bJSON modePrompt CacheTool use	992K	128K	Input$1.76Output$5.29/1M	—	—
qwen3.8-27bJSON modePrompt CacheTool useVision	992K	128K	Input$0.4412Output$1.76/1M	—	—
qwen3.8-flashJSON modePrompt CacheTool useVision	992K	128K	Input$0.1176Output$0.3971/1M	—	—
qwen3.8-maxJSON modePrompt CacheTool useVision	992K	128K	Input$1.76Output$5.29/1M	—	—
qwen3.6-max-previewTool use	256K	64K	Input$1.43Output$8.60/1M	—	—
qwen-flashPrompt Cache	998K	32K	Input$0.0221Output$0.2206/1M	—	—
qwen-plusPrompt Cache	998K	32K	Input$0.1176Output$0.2941/1M	—	—
qwen3.5-flashPrompt Cache	992K	64K	Input$0.0294Output$0.2941/1M	—	—
qwen3.5-plusPrompt Cache	992K	64K	Input$0.1176Output$0.7059/1M	—	—
qwen3.7-maxPrompt Cache	992K	64K	Input$1.76Output$5.29/1M	—	—
qwen3.7-plusPrompt Cache	992K	64K	Input$0.2941Output$1.18/1M	—	—
qwen3-vl-plusPrompt CacheVision	260K	32K	Input$0.1471Output$1.47/1M	—	—
qwen-doc-turboPrompt Cache	254K	8K	Input$0.0882Output$0.1471/1M	—	—
qwen-plus-characterPrompt Cache	32K	4K	Input$0.1176Output$0.2941/1M	—	—
qwen-maxPrompt Cache	31K	8K	Input$0.3529Output$1.41/1M	—	—
qwen-flash-characterPrompt Cache	8K	4K	Input$0.0368Output$0.2206/1M	—	—
qwen-deep-research	998K	32K	Input$7.94Output$23.97/1M	—	—
qwen3.5-27b	260K	64K	Input$0.0882Output$0.7059/1M	—	—
qwen3.5-omni-flashVision	197K	64K	Input$2.65Output$10.59/1M	—	—
qwen3.5-omni-plusVision	197K	64K	Input$7.79Output$31.32/1M	—	—
qwen3.6-27bTool useVision	128K	32K	Input$0.4412Output$2.65/1M	—	—
qwen3-omni-flashVision	49K	16K	Input$0.2647Output$1.01/1M	—	—
qwen3.5-ocrVision	49K	16K	Input$0.0735Output$0.2941/1M	—	—

1 / 4

All model series

6 series

Qwen TTS

Alibaba Cloud

AudioText to speechMusic+1

Auto from $11.76 · Per 1M characters

4 modelsOpen series

Qwen 3 / QwQ

Alibaba Cloud

ChatVisionCode+1

Auto from $0.0294 · Per 1M tokens

13 modelsOpen series

Wan

Alibaba Cloud

ImageVideo

Auto pricing units vary by model

11 modelsOpen series

Qwen

Alibaba Cloud

Chat

Auto from $0.0221 · Per 1M tokens

10 modelsOpen series

Qwen ASR

Alibaba Cloud

AudioSpeech to Text

Auto from $0.00001177 · Per second

10 modelsOpen series

Qwen Image

Alibaba Cloud

Save 10%-85%

Image

Auto from $0.0075 · Per image

8 modelsOpen series